def evaluate_dataset(classifier,data):
evaluation = Evaluation(data)
output = PlainText()
output.setHeader(data)
eval_buffer = StringBuffer() # buffer to use
output.setBuffer(eval_buffer)
options = [output]
evaluation.evaluateModel(classifier,data,options)
return evaluation
# check commandline parameters
if (not (len(sys.argv) == 2)):
print "Usage: UsingJ48Ext.py <ARFF-file>"
sys.exit()
# load data file
print "Loading data..."
file = FileReader(sys.argv[1])
data = Instances(file)
# set the class Index - the index of the dependent variable
data.setClassIndex(data.numAttributes() - 1)
# create the model
evaluation = Evaluation(data)
output = PlainText() # plain text output for predictions
output.setHeader(data)
buffer = StringBuffer() # buffer to use
output.setBuffer(buffer)
attRange = Range() # no additional attributes output
outputDistribution = Boolean(False) # we don't want distribution
j48 = J48()
j48.buildClassifier(data) # only a trained classifier can be evaluated
evaluation.evaluateModel(j48, data, [output, attRange, outputDistribution])
# print out the built model
print "--> Generated model:\n"
print j48
print "--> Evaluation:\n"
print evaluation.toSummaryString()
